Merge tag 'net-next-6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Paolo Abeni:
 "Core:

   - Increase size limits for to-be-sent skb frag allocations. This
     allows tun, tap devices and packet sockets to better cope with
     large writes operations

   - Store netdevs in an xarray, to simplify iterating over netdevs

   - Refactor nexthop selection for multipath routes

   - Improve sched class lifetime handling

   - Add backup nexthop ID support for bridge

   - Implement drop reasons support in openvswitch

   - Several data races annotations and fixes

   - Constify the sk parameter of routing functions

   - Prepend kernel version to netconsole message

  Protocols:

   - Implement support for TCP probing the peer being under memory
     pressure

   - Remove hard coded limitation on IPv6 specific info placement inside
     the socket struct

   - Get rid of sysctl_tcp_adv_win_scale and use an auto-estimated per
     socket scaling factor

   - Scaling-up the IPv6 expired route GC via a separated list of
     expiring routes

   - In-kernel support for the TLS alert protocol

   - Better support for UDP reuseport with connected sockets

   - Add NEXT-C-SID support for SRv6 End.X behavior, reducing the SR
     header size

   - Get rid of additional ancillary per MPTCP connection struct socket

   - Implement support for BPF-based MPTCP packet schedulers

   - Format MPTCP subtests selftests results in TAP

   - Several new SMC 2.1 features including unique experimental options,
     max connections per lgr negotiation, max links per lgr negotiation

  BPF:

   - Multi-buffer support in AF_XDP

   - Add multi uprobe BPF links for attaching multiple uprobes and usdt
     probes, which is significantly faster and saves extra fds

   - Implement an fd-based tc BPF attach API (TCX) and BPF link support
     on top of it

   - Add SO_REUSEPORT support for TC bpf_sk_assign

   - Support new instructions from cpu v4 to simplify the generated code
     and feature completeness, for x86, arm64, riscv64

   - Support defragmenting IPv(4|6) packets in BPF

   - Teach verifier actual bounds of bpf_get_smp_processor_id() and fix
     perf+libbpf issue related to custom section handling

   - Introduce bpf map element count and enable it for all program types

   - Add a BPF hook in sys_socket() to change the protocol ID from
     IPPROTO_TCP to IPPROTO_MPTCP to cover migration for legacy

   - Introduce bpf_me_mcache_free_rcu() and fix OOM under stress

   - Add uprobe support for the bpf_get_func_ip helper

   - Check skb ownership against full socket

   - Support for up to 12 arguments in BPF trampoline

   - Extend link_info for kprobe_multi and perf_event links

  Netfilter:

   - Speed-up process exit by aborting ruleset validation if a fatal
     signal is pending

   - Allow NLA_POLICY_MASK to be used with BE16/BE32 types

  Driver API:

   - Page pool optimizations, to improve data locality and cache usage

   - Introduce ndo_hwtstamp_get() and ndo_hwtstamp_set() to avoid the
     need for raw ioctl() handling in drivers

   - Simplify genetlink dump operations (doit/dumpit) providing them the
     common information already populated in struct genl_info

   - Extend and use the yaml devlink specs to [re]generate the split ops

   - Introduce devlink selective dumps, to allow SF filtering SF based
     on handle and other attributes

   - Add yaml netlink spec for netlink-raw families, allow route, link
     and address related queries via the ynl tool

   - Remove phylink legacy mode support

   - Support offload LED blinking to phy

   - Add devlink port function attributes for IPsec

  New hardware / drivers:

   - Ethernet:
      - Broadcom ASP 2.0 (72165) ethernet controller
      - MediaTek MT7988 SoC
      - Texas Instruments AM654 SoC
      - Texas Instruments IEP driver
      - Atheros qca8081 phy
      - Marvell 88Q2110 phy
      - NXP TJA1120 phy

   - WiFi:
      - MediaTek mt7981 support

   - Can:
      - Kvaser SmartFusion2 PCI Express devices
      - Allwinner T113 controllers
      - Texas Instruments tcan4552/4553 chips

   - Bluetooth:
      - Intel Gale Peak
      - Qualcomm WCN3988 and WCN7850
      - NXP AW693 and IW624
      - Mediatek MT2925

  Drivers:

   - Ethernet NICs:
      - nVidia/Mellanox:
         - mlx5:
            - support UDP encapsulation in packet offload mode
            - IPsec packet offload support in eswitch mode
            - improve aRFS observability by adding new set of counters
            - extends MACsec offload support to cover RoCE traffic
            - dynamic completion EQs
         - mlx4:
            - convert to use auxiliary bus instead of custom interface
              logic
      - Intel
         - ice:
            - implement switchdev bridge offload, even for LAG
              interfaces
            - implement SRIOV support for LAG interfaces
         - igc:
            - add support for multiple in-flight TX timestamps
      - Broadcom:
         - bnxt:
            - use the unified RX page pool buffers for XDP and non-XDP
            - use the NAPI skb allocation cache
      - OcteonTX2:
         - support Round Robin scheduling HTB offload
         - TC flower offload support for SPI field
      - Freescale:
         - add XDP_TX feature support
      - AMD:
         - ionic: add support for PCI FLR event
         - sfc:
            - basic conntrack offload
            - introduce eth, ipv4 and ipv6 pedit offloads
      - ST Microelectronics:
         - stmmac: maximze PTP timestamping resolution

   - Virtual NICs:
      - Microsoft vNIC:
         - batch ringing RX queue doorbell on receiving packets
         - add page pool for RX buffers
      - Virtio vNIC:
         - add per queue interrupt coalescing support
      - Google vNIC:
         - add queue-page-list mode support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add port range matching tc-flower offload
         - permit enslavement to netdevices with uppers

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - convert to phylink_pcs
      - Renesas:
         - r8A779fx: add speed change support
         - rzn1: enables vlan support

   - Ethernet PHYs:
      - convert mv88e6xxx to phylink_pcs

   - WiFi:
      - Qualcomm Wi-Fi 7 (ath12k):
         - extremely High Throughput (EHT) PHY support
      - RealTek (rtl8xxxu):
         - enable AP mode for: RTL8192FU, RTL8710BU (RTL8188GU),
           RTL8192EU and RTL8723BU
      - RealTek (rtw89):
         - Introduce Time Averaged SAR (TAS) support

   - Connector:
      - support for event filtering"

* tag 'net-next-6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1806 commits)
  net: ethernet: mtk_wed: minor change in wed_{tx,rx}info_show
  net: ethernet: mtk_wed: add some more info in wed_txinfo_show handler
  net: stmmac: clarify difference between "interface" and "phy_interface"
  r8152: add vendor/device ID pair for D-Link DUB-E250
  devlink: move devlink_notify_register/unregister() to dev.c
  devlink: move small_ops definition into netlink.c
  devlink: move tracepoint definitions into core.c
  devlink: push linecard related code into separate file
  devlink: push rate related code into separate file
  devlink: push trap related code into separate file
  devlink: use tracepoint_enabled() helper
  devlink: push region related code into separate file
  devlink: push param related code into separate file
  devlink: push resource related code into separate file
  devlink: push dpipe related code into separate file
  devlink: move and rename devlink_dpipe_send_and_alloc_skb() helper
  devlink: push shared buffer related code into separate file
  devlink: push port related code into separate file
  devlink: push object register/unregister notifications into separate helpers
  inet: fix IP_TRANSPARENT error handling
  ...

8 files changed, 298 insertions, 60 deletions

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index f5834af5fad5..bacdd971615e 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -641,20 +641,22 @@ static int smcr_clnt_conf_first_link(struct smc_sock *smc)
 	smc_llc_link_active(link);
 	smcr_lgr_set_type(link->lgr, SMC_LGR_SINGLE);
 
-	/* optional 2nd link, receive ADD LINK request from server */
-	qentry = smc_llc_wait(link->lgr, NULL, SMC_LLC_WAIT_TIME,
-			      SMC_LLC_ADD_LINK);
-	if (!qentry) {
-		struct smc_clc_msg_decline dclc;
-
-		rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc),
-				      SMC_CLC_DECLINE, CLC_WAIT_TIME_SHORT);
-		if (rc == -EAGAIN)
-			rc = 0; /* no DECLINE received, go with one link */
-		return rc;
+	if (link->lgr->max_links > 1) {
+		/* optional 2nd link, receive ADD LINK request from server */
+		qentry = smc_llc_wait(link->lgr, NULL, SMC_LLC_WAIT_TIME,
+				      SMC_LLC_ADD_LINK);
+		if (!qentry) {
+			struct smc_clc_msg_decline dclc;
+
+			rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc),
+					      SMC_CLC_DECLINE, CLC_WAIT_TIME_SHORT);
+			if (rc == -EAGAIN)
+				rc = 0; /* no DECLINE received, go with one link */
+			return rc;
+		}
+		smc_llc_flow_qentry_clr(&link->lgr->llc_flow_lcl);
+		smc_llc_cli_add_link(link, qentry);
 	}
-	smc_llc_flow_qentry_clr(&link->lgr->llc_flow_lcl);
-	smc_llc_cli_add_link(link, qentry);
 	return 0;
 }
 
@@ -1144,7 +1146,7 @@ static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc,
 
 #define SMC_CLC_MAX_ACCEPT_LEN \
 	(sizeof(struct smc_clc_msg_accept_confirm_v2) + \
-	 sizeof(struct smc_clc_first_contact_ext) + \
+	 sizeof(struct smc_clc_first_contact_ext_v2x) + \
 	 sizeof(struct smc_clc_msg_trail))
 
 /* CLC handshake during connect */
@@ -1198,8 +1200,8 @@ static int smc_connect_rdma_v2_prepare(struct smc_sock *smc,
 	struct smc_clc_msg_accept_confirm_v2 *clc_v2 =
 		(struct smc_clc_msg_accept_confirm_v2 *)aclc;
 	struct smc_clc_first_contact_ext *fce =
-		(struct smc_clc_first_contact_ext *)
-			(((u8 *)clc_v2) + sizeof(*clc_v2));
+		smc_get_clc_first_contact_ext(clc_v2, false);
+	int rc;
 
 	if (!ini->first_contact_peer || aclc->hdr.version == SMC_V1)
 		return 0;
@@ -1218,6 +1220,12 @@ static int smc_connect_rdma_v2_prepare(struct smc_sock *smc,
 			return SMC_CLC_DECL_NOINDIRECT;
 		}
 	}
+
+	ini->release_nr = fce->release;
+	rc = smc_clc_clnt_v2x_features_validate(fce, ini);
+	if (rc)
+		return rc;
+
 	return 0;
 }
 
@@ -1236,6 +1244,8 @@ static int smc_connect_rdma(struct smc_sock *smc,
 	memcpy(ini->peer_systemid, aclc->r0.lcl.id_for_peer, SMC_SYSTEMID_LEN);
 	memcpy(ini->peer_gid, aclc->r0.lcl.gid, SMC_GID_SIZE);
 	memcpy(ini->peer_mac, aclc->r0.lcl.mac, ETH_ALEN);
+	ini->max_conns = SMC_CONN_PER_LGR_MAX;
+	ini->max_links = SMC_LINKS_ADD_LNK_MAX;
 
 	reason_code = smc_connect_rdma_v2_prepare(smc, aclc, ini);
 	if (reason_code)
@@ -1386,6 +1396,16 @@ static int smc_connect_ism(struct smc_sock *smc,
 		struct smc_clc_msg_accept_confirm_v2 *aclc_v2 =
 			(struct smc_clc_msg_accept_confirm_v2 *)aclc;
 
+		if (ini->first_contact_peer) {
+			struct smc_clc_first_contact_ext *fce =
+				smc_get_clc_first_contact_ext(aclc_v2, true);
+
+			ini->release_nr = fce->release;
+			rc = smc_clc_clnt_v2x_features_validate(fce, ini);
+			if (rc)
+				return rc;
+		}
+
 		rc = smc_v2_determine_accepted_chid(aclc_v2, ini);
 		if (rc)
 			return rc;
@@ -1420,7 +1440,7 @@ static int smc_connect_ism(struct smc_sock *smc,
 	}
 
 	rc = smc_clc_send_confirm(smc, ini->first_contact_local,
-				  aclc->hdr.version, eid, NULL);
+				  aclc->hdr.version, eid, ini);
 	if (rc)
 		goto connect_abort;
 	mutex_unlock(&smc_server_lgr_pending);
@@ -1820,7 +1840,7 @@ void smc_close_non_accepted(struct sock *sk)
 	lock_sock(sk);
 	if (!sk->sk_lingertime)
 		/* wait for peer closing */
-		sk->sk_lingertime = SMC_MAX_STREAM_WAIT_TIMEOUT;
+		WRITE_ONCE(sk->sk_lingertime, SMC_MAX_STREAM_WAIT_TIMEOUT);
 	__smc_release(smc);
 	release_sock(sk);
 	sock_put(sk); /* sock_hold above */
@@ -1870,10 +1890,12 @@ static int smcr_serv_conf_first_link(struct smc_sock *smc)
 	smc_llc_link_active(link);
 	smcr_lgr_set_type(link->lgr, SMC_LGR_SINGLE);
 
-	down_write(&link->lgr->llc_conf_mutex);
-	/* initial contact - try to establish second link */
-	smc_llc_srv_add_link(link, NULL);
-	up_write(&link->lgr->llc_conf_mutex);
+	if (link->lgr->max_links > 1) {
+		down_write(&link->lgr->llc_conf_mutex);
+		/* initial contact - try to establish second link */
+		smc_llc_srv_add_link(link, NULL);
+		up_write(&link->lgr->llc_conf_mutex);
+	}
 	return 0;
 }
 
@@ -1996,6 +2018,10 @@ static int smc_listen_v2_check(struct smc_sock *new_smc,
 		}
 	}
 
+	ini->release_nr = pclc_v2_ext->hdr.flag.release;
+	if (pclc_v2_ext->hdr.flag.release > SMC_RELEASE)
+		ini->release_nr = SMC_RELEASE;
+
 out:
 	if (!ini->smcd_version && !ini->smcr_version)
 		return rc;
@@ -2430,6 +2456,10 @@ static void smc_listen_work(struct work_struct *work)
 	if (rc)
 		goto out_decl;
 
+	rc = smc_clc_srv_v2x_features_validate(pclc, ini);
+	if (rc)
+		goto out_decl;
+
 	mutex_lock(&smc_server_lgr_pending);
 	smc_close_init(new_smc);
 	smc_rx_init(new_smc);
@@ -2443,7 +2473,7 @@ static void smc_listen_work(struct work_struct *work)
 	/* send SMC Accept CLC message */
 	accept_version = ini->is_smcd ? ini->smcd_version : ini->smcr_version;
 	rc = smc_clc_send_accept(new_smc, ini->first_contact_local,
-				 accept_version, ini->negotiated_eid);
+				 accept_version, ini->negotiated_eid, ini);
 	if (rc)
 		goto out_unlock;
 
@@ -2462,6 +2492,18 @@ static void smc_listen_work(struct work_struct *work)
 		goto out_decl;
 	}
 
+	rc = smc_clc_v2x_features_confirm_check(cclc, ini);
+	if (rc) {
+		if (!ini->is_smcd)
+			goto out_unlock;
+		goto out_decl;
+	}
+
+	/* fce smc release version is needed in smc_listen_rdma_finish,
+	 * so save fce info here.
+	 */
+	smc_conn_save_peer_info_fce(new_smc, cclc);
+
 	/* finish worker */
 	if (!ini->is_smcd) {
 		rc = smc_listen_rdma_finish(new_smc, cclc,
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 1f2b912c43d1..24745fde4ac2 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -21,7 +21,10 @@
 
 #define SMC_V1		1		/* SMC version V1 */
 #define SMC_V2		2		/* SMC version V2 */
-#define SMC_RELEASE	0
+
+#define SMC_RELEASE_0 0
+#define SMC_RELEASE_1 1
+#define SMC_RELEASE	SMC_RELEASE_1 /* the latest release version */
 
 #define SMCPROTO_SMC		0	/* SMC protocol, IPv4 */
 #define SMCPROTO_SMC6		1	/* SMC protocol, IPv6 */
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index c90d9e5dda54..8deb46c28f1d 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -391,9 +391,7 @@ smc_clc_msg_acc_conf_valid(struct smc_clc_msg_accept_confirm_v2 *clc_v2)
 			return false;
 	} else {
 		if (hdr->typev1 == SMC_TYPE_D &&
-		    ntohs(hdr->length) != SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 &&
-		    (ntohs(hdr->length) != SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 +
-				sizeof(struct smc_clc_first_contact_ext)))
+		    ntohs(hdr->length) < SMCD_CLC_ACCEPT_CONFIRM_LEN_V2)
 			return false;
 		if (hdr->typev1 == SMC_TYPE_R &&
 		    ntohs(hdr->length) < SMCR_CLC_ACCEPT_CONFIRM_LEN_V2)
@@ -420,13 +418,29 @@ smc_clc_msg_decl_valid(struct smc_clc_msg_decline *dclc)
 	return true;
 }
 
-static void smc_clc_fill_fce(struct smc_clc_first_contact_ext *fce, int *len)
+static int smc_clc_fill_fce(struct smc_clc_first_contact_ext_v2x *fce,
+			    struct smc_init_info *ini)
 {
+	int ret = sizeof(*fce);
+
 	memset(fce, 0, sizeof(*fce));
-	fce->os_type = SMC_CLC_OS_LINUX;
-	fce->release = SMC_RELEASE;
-	memcpy(fce->hostname, smc_hostname, sizeof(smc_hostname));
-	(*len) += sizeof(*fce);
+	fce->fce_v2_base.os_type = SMC_CLC_OS_LINUX;
+	fce->fce_v2_base.release = ini->release_nr;
+	memcpy(fce->fce_v2_base.hostname, smc_hostname, sizeof(smc_hostname));
+	if (ini->is_smcd && ini->release_nr < SMC_RELEASE_1) {
+		ret = sizeof(struct smc_clc_first_contact_ext);
+		goto out;
+	}
+
+	if (ini->release_nr >= SMC_RELEASE_1) {
+		if (!ini->is_smcd) {
+			fce->max_conns = ini->max_conns;
+			fce->max_links = ini->max_links;
+		}
+	}
+
+out:
+	return ret;
 }
 
 /* check if received message has a correct header length and contains valid
@@ -927,8 +941,11 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
 				sizeof(struct smc_clc_smcd_gid_chid);
 		}
 	}
-	if (smcr_indicated(ini->smc_type_v2))
+	if (smcr_indicated(ini->smc_type_v2)) {
 		memcpy(v2_ext->roce, ini->smcrv2.ib_gid_v2, SMC_GID_SIZE);
+		v2_ext->max_conns = SMC_CONN_PER_LGR_PREFER;
+		v2_ext->max_links = SMC_LINKS_PER_LGR_MAX_PREFER;
+	}
 
 	pclc_base->hdr.length = htons(plen);
 	memcpy(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
@@ -986,13 +1003,13 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc,
 				       u8 *eid, struct smc_init_info *ini)
 {
 	struct smc_connection *conn = &smc->conn;
+	struct smc_clc_first_contact_ext_v2x fce;
 	struct smc_clc_msg_accept_confirm *clc;
-	struct smc_clc_first_contact_ext fce;
 	struct smc_clc_fce_gid_ext gle;
 	struct smc_clc_msg_trail trl;
+	int i, len, fce_len;
 	struct kvec vec[5];
 	struct msghdr msg;
-	int i, len;
 
 	/* send SMC Confirm CLC msg */
 	clc = (struct smc_clc_msg_accept_confirm *)clc_v2;
@@ -1018,8 +1035,10 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc,
 			if (eid && eid[0])
 				memcpy(clc_v2->d1.eid, eid, SMC_MAX_EID_LEN);
 			len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2;
-			if (first_contact)
-				smc_clc_fill_fce(&fce, &len);
+			if (first_contact) {
+				fce_len = smc_clc_fill_fce(&fce, ini);
+				len += fce_len;
+			}
 			clc_v2->hdr.length = htons(len);
 		}
 		memcpy(trl.eyecatcher, SMCD_EYECATCHER,
@@ -1063,15 +1082,14 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc,
 				memcpy(clc_v2->r1.eid, eid, SMC_MAX_EID_LEN);
 			len = SMCR_CLC_ACCEPT_CONFIRM_LEN_V2;
 			if (first_contact) {
-				smc_clc_fill_fce(&fce, &len);
-				fce.v2_direct = !link->lgr->uses_gateway;
-				memset(&gle, 0, sizeof(gle));
-				if (ini && clc->hdr.type == SMC_CLC_CONFIRM) {
+				fce_len = smc_clc_fill_fce(&fce, ini);
+				len += fce_len;
+				fce.fce_v2_base.v2_direct = !link->lgr->uses_gateway;
+				if (clc->hdr.type == SMC_CLC_CONFIRM) {
+					memset(&gle, 0, sizeof(gle));
 					gle.gid_cnt = ini->smcrv2.gidlist.len;
 					len += sizeof(gle);
 					len += gle.gid_cnt * sizeof(gle.gid[0]);
-				} else {
-					len += sizeof(gle.reserved);
 				}
 			}
 			clc_v2->hdr.length = htons(len);
@@ -1094,7 +1112,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc,
 				   sizeof(trl);
 	if (version > SMC_V1 && first_contact) {
 		vec[i].iov_base = &fce;
-		vec[i++].iov_len = sizeof(fce);
+		vec[i++].iov_len = fce_len;
 		if (!conn->lgr->is_smcd) {
 			if (clc->hdr.type == SMC_CLC_CONFIRM) {
 				vec[i].iov_base = &gle;
@@ -1102,9 +1120,6 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc,
 				vec[i].iov_base = &ini->smcrv2.gidlist.list;
 				vec[i++].iov_len = gle.gid_cnt *
 						   sizeof(gle.gid[0]);
-			} else {
-				vec[i].iov_base = &gle.reserved;
-				vec[i++].iov_len = sizeof(gle.reserved);
 			}
 		}
 	}
@@ -1141,7 +1156,7 @@ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact,
 
 /* send CLC ACCEPT message across internal TCP socket */
 int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact,
-			u8 version, u8 *negotiated_eid)
+			u8 version, u8 *negotiated_eid, struct smc_init_info *ini)
 {
 	struct smc_clc_msg_accept_confirm_v2 aclc_v2;
 	int len;
@@ -1149,13 +1164,95 @@ int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact,
 	memset(&aclc_v2, 0, sizeof(aclc_v2));
 	aclc_v2.hdr.type = SMC_CLC_ACCEPT;
 	len = smc_clc_send_confirm_accept(new_smc, &aclc_v2, srv_first_contact,
-					  version, negotiated_eid, NULL);
+					  version, negotiated_eid, ini);
 	if (len < ntohs(aclc_v2.hdr.length))
 		len = len >= 0 ? -EPROTO : -new_smc->clcsock->sk->sk_err;
 
 	return len > 0 ? 0 : len;
 }
 
+int smc_clc_srv_v2x_features_validate(struct smc_clc_msg_proposal *pclc,
+				      struct smc_init_info *ini)
+{
+	struct smc_clc_v2_extension *pclc_v2_ext;
+
+	ini->max_conns = SMC_CONN_PER_LGR_MAX;
+	ini->max_links = SMC_LINKS_ADD_LNK_MAX;
+
+	if ((!(ini->smcd_version & SMC_V2) && !(ini->smcr_version & SMC_V2)) ||
+	    ini->release_nr < SMC_RELEASE_1)
+		return 0;
+
+	pclc_v2_ext = smc_get_clc_v2_ext(pclc);
+	if (!pclc_v2_ext)
+		return SMC_CLC_DECL_NOV2EXT;
+
+	if (ini->smcr_version & SMC_V2) {
+		ini->max_conns = min_t(u8, pclc_v2_ext->max_conns, SMC_CONN_PER_LGR_PREFER);
+		if (ini->max_conns < SMC_CONN_PER_LGR_MIN)
+			return SMC_CLC_DECL_MAXCONNERR;
+
+		ini->max_links = min_t(u8, pclc_v2_ext->max_links, SMC_LINKS_PER_LGR_MAX_PREFER);
+		if (ini->max_links < SMC_LINKS_ADD_LNK_MIN)
+			return SMC_CLC_DECL_MAXLINKERR;
+	}
+
+	return 0;
+}
+
+int smc_clc_clnt_v2x_features_validate(struct smc_clc_first_contact_ext *fce,
+				       struct smc_init_info *ini)
+{
+	struct smc_clc_first_contact_ext_v2x *fce_v2x =
+		(struct smc_clc_first_contact_ext_v2x *)fce;
+
+	if (ini->release_nr < SMC_RELEASE_1)
+		return 0;
+
+	if (!ini->is_smcd) {
+		if (fce_v2x->max_conns < SMC_CONN_PER_LGR_MIN)
+			return SMC_CLC_DECL_MAXCONNERR;
+		ini->max_conns = fce_v2x->max_conns;
+
+		if (fce_v2x->max_links > SMC_LINKS_ADD_LNK_MAX ||
+		    fce_v2x->max_links < SMC_LINKS_ADD_LNK_MIN)
+			return SMC_CLC_DECL_MAXLINKERR;
+		ini->max_links = fce_v2x->max_links;
+	}
+
+	return 0;
+}
+
+int smc_clc_v2x_features_confirm_check(struct smc_clc_msg_accept_confirm *cclc,
+				       struct smc_init_info *ini)
+{
+	struct smc_clc_msg_accept_confirm_v2 *clc_v2 =
+		(struct smc_clc_msg_accept_confirm_v2 *)cclc;
+	struct smc_clc_first_contact_ext *fce =
+		smc_get_clc_first_contact_ext(clc_v2, ini->is_smcd);
+	struct smc_clc_first_contact_ext_v2x *fce_v2x =
+		(struct smc_clc_first_contact_ext_v2x *)fce;
+
+	if (cclc->hdr.version == SMC_V1 ||
+	    !(cclc->hdr.typev2 & SMC_FIRST_CONTACT_MASK))
+		return 0;
+
+	if (ini->release_nr != fce->release)
+		return SMC_CLC_DECL_RELEASEERR;
+
+	if (fce->release < SMC_RELEASE_1)
+		return 0;
+
+	if (!ini->is_smcd) {
+		if (fce_v2x->max_conns != ini->max_conns)
+			return SMC_CLC_DECL_MAXCONNERR;
+		if (fce_v2x->max_links != ini->max_links)
+			return SMC_CLC_DECL_MAXLINKERR;
+	}
+
+	return 0;
+}
+
 void smc_clc_get_hostname(u8 **host)
 {
 	*host = &smc_hostname[0];
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index 5fee545c9a10..c5c8e7db775a 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -45,6 +45,9 @@
 #define SMC_CLC_DECL_NOSEID	0x03030006  /* peer sent no SEID	      */
 #define SMC_CLC_DECL_NOSMCD2DEV	0x03030007  /* no SMC-Dv2 device found	      */
 #define SMC_CLC_DECL_NOUEID	0x03030008  /* peer sent no UEID	      */
+#define SMC_CLC_DECL_RELEASEERR	0x03030009  /* release version negotiate failed */
+#define SMC_CLC_DECL_MAXCONNERR	0x0303000a  /* max connections negotiate failed */
+#define SMC_CLC_DECL_MAXLINKERR	0x0303000b  /* max links negotiate failed */
 #define SMC_CLC_DECL_MODEUNSUPP	0x03040000  /* smc modes do not match (R or D)*/
 #define SMC_CLC_DECL_RMBE_EC	0x03050000  /* peer has eyecatcher in RMBE    */
 #define SMC_CLC_DECL_OPTUNSUPP	0x03060000  /* fastopen sockopt not supported */
@@ -133,7 +136,9 @@ struct smc_clc_smcd_gid_chid {
 struct smc_clc_v2_extension {
 	struct smc_clnt_opts_area_hdr hdr;
 	u8 roce[16];		/* RoCEv2 GID */
-	u8 reserved[16];
+	u8 max_conns;
+	u8 max_links;
+	u8 reserved[14];
 	u8 user_eids[][SMC_MAX_EID_LEN];
 };
 
@@ -147,7 +152,9 @@ struct smc_clc_msg_proposal_prefix {	/* prefix part of clc proposal message*/
 struct smc_clc_msg_smcd {	/* SMC-D GID information */
 	struct smc_clc_smcd_gid_chid ism; /* ISM native GID+CHID of requestor */
 	__be16 v2_ext_offset;	/* SMC Version 2 Extension Offset */
-	u8 reserved[28];
+	u8 vendor_oui[3];	/* vendor organizationally unique identifier */
+	u8 vendor_exp_options[5];
+	u8 reserved[20];
 };
 
 struct smc_clc_smcd_v2_extension {
@@ -231,8 +238,19 @@ struct smc_clc_first_contact_ext {
 	u8 hostname[SMC_MAX_HOSTNAME_LEN];
 };
 
+struct smc_clc_first_contact_ext_v2x {
+	struct smc_clc_first_contact_ext fce_v2_base;
+	u8 max_conns; /* for SMC-R only */
+	u8 max_links; /* for SMC-R only */
+	u8 reserved3[2];
+	__be32 vendor_exp_options;
+	u8 reserved4[8];
+} __packed;		/* format defined in
+			 * IBM Shared Memory Communications Version 2 (Third Edition)
+			 * (https://www.ibm.com/support/pages/node/7009315)
+			 */
+
 struct smc_clc_fce_gid_ext {
-	u8 reserved[16];
 	u8 gid_cnt;
 	u8 reserved2[3];
 	u8 gid[][SMC_GID_SIZE];
@@ -370,6 +388,27 @@ smc_get_clc_smcd_v2_ext(struct smc_clc_v2_extension *prop_v2ext)
 		 ntohs(prop_v2ext->hdr.smcd_v2_ext_offset));
 }
 
+static inline struct smc_clc_first_contact_ext *
+smc_get_clc_first_contact_ext(struct smc_clc_msg_accept_confirm_v2 *clc_v2,
+			      bool is_smcd)
+{
+	int clc_v2_len;
+
+	if (clc_v2->hdr.version == SMC_V1 ||
+	    !(clc_v2->hdr.typev2 & SMC_FIRST_CONTACT_MASK))
+		return NULL;
+
+	if (is_smcd)
+		clc_v2_len =
+			offsetofend(struct smc_clc_msg_accept_confirm_v2, d1);
+	else
+		clc_v2_len =
+			offsetofend(struct smc_clc_msg_accept_confirm_v2, r1);
+
+	return (struct smc_clc_first_contact_ext *)(((u8 *)clc_v2) +
+						    clc_v2_len);
+}
+
 struct smcd_dev;
 struct smc_init_info;
 
@@ -382,7 +421,13 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini);
 int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact,
 			 u8 version, u8 *eid, struct smc_init_info *ini);
 int smc_clc_send_accept(struct smc_sock *smc, bool srv_first_contact,
-			u8 version, u8 *negotiated_eid);
+			u8 version, u8 *negotiated_eid, struct smc_init_info *ini);
+int smc_clc_srv_v2x_features_validate(struct smc_clc_msg_proposal *pclc,
+				      struct smc_init_info *ini);
+int smc_clc_clnt_v2x_features_validate(struct smc_clc_first_contact_ext *fce,
+				       struct smc_init_info *ini);
+int smc_clc_v2x_features_confirm_check(struct smc_clc_msg_accept_confirm *cclc,
+				       struct smc_init_info *ini);
 void smc_clc_init(void) __init;
 void smc_clc_exit(void);
 void smc_clc_get_hostname(u8 **host);
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 6b78075404d7..bd01dd31e4bd 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -319,6 +319,10 @@ static int smc_nl_fill_smcr_lgr_v2(struct smc_link_group *lgr,
 		goto errattr;
 	if (nla_put_u8(skb, SMC_NLA_LGR_R_V2_DIRECT, !lgr->uses_gateway))
 		goto errv2attr;
+	if (nla_put_u8(skb, SMC_NLA_LGR_R_V2_MAX_CONNS, lgr->max_conns))
+		goto errv2attr;
+	if (nla_put_u8(skb, SMC_NLA_LGR_R_V2_MAX_LINKS, lgr->max_links))
+		goto errv2attr;
 
 	nla_nest_end(skb, v2_attrs);
 	return 0;
@@ -895,9 +899,13 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini)
 			lgr->uses_gateway = ini->smcrv2.uses_gateway;
 			memcpy(lgr->nexthop_mac, ini->smcrv2.nexthop_mac,
 			       ETH_ALEN);
+			lgr->max_conns = ini->max_conns;
+			lgr->max_links = ini->max_links;
 		} else {
 			ibdev = ini->ib_dev;
 			ibport = ini->ib_port;
+			lgr->max_conns = SMC_CONN_PER_LGR_MAX;
+			lgr->max_links = SMC_LINKS_ADD_LNK_MAX;
 		}
 		memcpy(lgr->pnet_id, ibdev->pnetid[ibport - 1],
 		       SMC_MAX_PNETID_LEN);
@@ -1664,6 +1672,9 @@ void smcr_port_add(struct smc_ib_device *smcibdev, u8 ibport)
 		    !rdma_dev_access_netns(smcibdev->ibdev, lgr->net))
 			continue;
 
+		if (lgr->type == SMC_LGR_SINGLE && lgr->max_links <= 1)
+			continue;
+
 		/* trigger local add link processing */
 		link = smc_llc_usable_link(lgr);
 		if (link)
@@ -1888,7 +1899,7 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini)
 		    (ini->smcd_version == SMC_V2 ||
 		     lgr->vlan_id == ini->vlan_id) &&
 		    (role == SMC_CLNT || ini->is_smcd ||
-		    (lgr->conns_num < SMC_RMBS_PER_LGR_MAX &&
+		    (lgr->conns_num < lgr->max_conns &&
 		      !bitmap_full(lgr->rtokens_used_mask, SMC_RMBS_PER_LGR_MAX)))) {
 			/* link group found */
 			ini->first_contact_local = 0;
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 1645fba0d2d3..120027d40469 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -22,6 +22,15 @@
 #include "smc_ib.h"
 
 #define SMC_RMBS_PER_LGR_MAX	255	/* max. # of RMBs per link group */
+#define SMC_CONN_PER_LGR_MIN	16	/* min. # of connections per link group */
+#define SMC_CONN_PER_LGR_MAX	255	/* max. # of connections per link group,
+					 * also is the default value for SMC-R v1 and v2.0
+					 */
+#define SMC_CONN_PER_LGR_PREFER	255	/* Preferred connections per link group used for
+					 * SMC-R v2.1 and later negotiation, vendors or
+					 * distrubutions may modify it to a value between
+					 * 16-255 as needed.
+					 */
 
 struct smc_lgr_list {			/* list of link group definition */
 	struct list_head	list;
@@ -164,6 +173,15 @@ struct smc_link {
  */
 #define SMC_LINKS_PER_LGR_MAX	3
 #define SMC_SINGLE_LINK		0
+#define SMC_LINKS_ADD_LNK_MIN	1	/* min. # of links per link group */
+#define SMC_LINKS_ADD_LNK_MAX	2	/* max. # of links per link group, also is the
+					 * default value for smc-r v1.0 and v2.0
+					 */
+#define SMC_LINKS_PER_LGR_MAX_PREFER	2	/* Preferred max links per link group used for
+						 * SMC-R v2.1 and later negotiation, vendors or
+						 * distrubutions may modify it to a value between
+						 * 1-2 as needed.
+						 */
 
 /* tx/rx buffer list element for sndbufs list and rmbs list of a lgr */
 struct smc_buf_desc {
@@ -331,6 +349,10 @@ struct smc_link_group {
 			__be32			saddr;
 						/* net namespace */
 			struct net		*net;
+			u8			max_conns;
+						/* max conn can be assigned to lgr */
+			u8			max_links;
+						/* max links can be added in lgr */
 		};
 		struct { /* SMC-D */
 			u64			peer_gid;
@@ -374,6 +396,9 @@ struct smc_init_info {
 	u8			is_smcd;
 	u8			smc_type_v1;
 	u8			smc_type_v2;
+	u8			release_nr;
+	u8			max_conns;
+	u8			max_links;
 	u8			first_contact_peer;
 	u8			first_contact_local;
 	unsigned short		vlan_id;
@@ -539,7 +564,6 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini);
 
 void smc_conn_free(struct smc_connection *conn);
 int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini);
-void smc_lgr_schedule_free_work_fast(struct smc_link_group *lgr);
 int smc_core_init(void);
 void smc_core_exit(void);
 
diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
index 034295676e88..4df5f8c8a0a1 100644
--- a/net/smc/smc_ib.h
+++ b/net/smc/smc_ib.h
@@ -96,7 +96,6 @@ void smc_ib_destroy_queue_pair(struct smc_link *lnk);
 int smc_ib_create_queue_pair(struct smc_link *lnk);
 int smc_ib_ready_link(struct smc_link *lnk);
 int smc_ib_modify_qp_rts(struct smc_link *lnk);
-int smc_ib_modify_qp_reset(struct smc_link *lnk);
 int smc_ib_modify_qp_error(struct smc_link *lnk);
 long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev);
 int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index 90f0b60b196a..018ce8133b02 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -52,14 +52,13 @@ struct smc_llc_msg_confirm_link {	/* type 0x01 */
 	u8 link_num;
 	u8 link_uid[SMC_LGR_ID_SIZE];
 	u8 max_links;
-	u8 reserved[9];
+	u8 max_conns;
+	u8 reserved[8];
 };
 
 #define SMC_LLC_FLAG_ADD_LNK_REJ	0x40
 #define SMC_LLC_REJ_RSN_NO_ALT_PATH	1
 
-#define SMC_LLC_ADD_LNK_MAX_LINKS	2
-
 struct smc_llc_msg_add_link {		/* type 0x02 */
 	struct smc_llc_hdr hd;
 	u8 sender_mac[ETH_ALEN];
@@ -471,7 +470,12 @@ int smc_llc_send_confirm_link(struct smc_link *link,
 	hton24(confllc->sender_qp_num, link->roce_qp->qp_num);
 	confllc->link_num = link->link_id;
 	memcpy(confllc->link_uid, link->link_uid, SMC_LGR_ID_SIZE);
-	confllc->max_links = SMC_LLC_ADD_LNK_MAX_LINKS;
+	confllc->max_links = SMC_LINKS_ADD_LNK_MAX;
+	if (link->lgr->smc_version == SMC_V2 &&
+	    link->lgr->peer_smc_release >= SMC_RELEASE_1) {
+		confllc->max_conns = link->lgr->max_conns;
+		confllc->max_links = link->lgr->max_links;
+	}
 	/* send llc message */
 	rc = smc_wr_tx_send(link, pend);
 put_out:
@@ -1041,6 +1045,11 @@ int smc_llc_cli_add_link(struct smc_link *link, struct smc_llc_qentry *qentry)
 		goto out_reject;
 	}
 
+	if (lgr->type == SMC_LGR_SINGLE && lgr->max_links <= 1) {
+		rc = 0;
+		goto out_reject;
+	}
+
 	ini->vlan_id = lgr->vlan_id;
 	if (lgr->smc_version == SMC_V2) {
 		ini->check_smcrv2 = true;
@@ -1165,6 +1174,9 @@ static void smc_llc_cli_add_link_invite(struct smc_link *link,
 	    lgr->type == SMC_LGR_ASYMMETRIC_PEER)
 		goto out;
 
+	if (lgr->type == SMC_LGR_SINGLE && lgr->max_links <= 1)
+		goto out;
+
 	ini = kzalloc(sizeof(*ini), GFP_KERNEL);
 	if (!ini)
 		goto out;
@@ -1410,6 +1422,11 @@ int smc_llc_srv_add_link(struct smc_link *link,
 		goto out;
 	}
 
+	if (lgr->type == SMC_LGR_SINGLE && lgr->max_links <= 1) {
+		rc = 0;
+		goto out;
+	}
+
 	/* ignore client add link recommendation, start new flow */
 	ini->vlan_id = lgr->vlan_id;
 	if (lgr->smc_version == SMC_V2) {